INDEX

Explanations

terms related to public relations and communication

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shall

-0.16

azy

-0.15

Ihr

-0.14

endon

-0.14

ÙĨ

-0.14

igua

-0.14

ined

-0.14

lan

-0.13

olian

-0.13

ìľ¨

-0.13

POSITIVE LOGITS

/private

0.17

-private

0.16

itaire

0.16

/commons

0.15

/Public

0.15

lyph

0.15

/public

0.15

å®Ŀ

0.14

edBy

0.14

_html

0.14

Activations Density 0.046%

terms related to public relations and communication

No Comments

No Known Activations